{"total":53,"rows":[{"id":"2509.03493","title":"On Entropy Control in LLM-RL Algorithms","created":"2025-09-03","cited_by_count":40,"area":null},{"id":"2111.02552","title":"Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies","created":"2021-11-03","cited_by_count":38,"area":null},{"id":"2111.03466","title":"Learning Large Neighborhood Search Policy for Integer Programming","created":"2021-11-01","cited_by_count":35,"area":null},{"id":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24,"area":null},{"id":"2110.10149","title":"Continuous Control with Action Quantization from Demonstrations","created":"2021-10-19","cited_by_count":22,"area":null},{"id":"2109.03540","title":"A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions","created":"2021-09-08","cited_by_count":21,"area":null},{"id":"2109.06449","title":"Deep hierarchical reinforcement agents for automated penetration testing","created":"2021-09-14","cited_by_count":19,"area":null},{"id":"2108.13680","title":"Learning Practically Feasible Policies for Online 3D Bin Packing","created":"2021-08-31","cited_by_count":18,"area":null},{"id":"2302.04903","title":"AdaptSim: Task-Driven Simulation Adaptation for Sim-to-Real Transfer","created":"2023-02-09","cited_by_count":18,"area":null},{"id":"2310.03173","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","created":"2023-10-04","cited_by_count":17,"area":null},{"id":"2201.09058","title":"DeepScalper: A Risk-Aware Reinforcement Learning Framework to Capture Fleeting Intraday Trading Opportunities","created":"2021-12-15","cited_by_count":15,"area":null},{"id":"2112.09012","title":"Centralizing State-Values in Dueling Networks for Multi-Robot Reinforcement Learning Mapless Navigation","created":"2021-12-16","cited_by_count":13,"area":null},{"id":"2205.03793","title":"Pervasive Machine Learning for Smart Radio Environments Enabled by Reconfigurable Intelligent Surfaces","created":"2022-05-08","cited_by_count":12,"area":null},{"id":"2308.02594","title":"SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agents","created":"2023-08-03","cited_by_count":10,"area":null},{"id":"2108.07041","title":"Implicitly Regularized RL with Implicit Q-Values","created":"2021-08-16","cited_by_count":9,"area":null},{"id":"2303.11899","title":"Large-Scale Traffic Signal Control Using Constrained Network Partition and Adaptive Deep Reinforcement Learning","created":"2023-03-21","cited_by_count":6,"area":null},{"id":"2312.06258","title":"No Prior Mask: Eliminate Redundant Action for Deep Reinforcement Learning","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2106.05665","title":"Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception","created":"2021-06-10","cited_by_count":5,"area":null},{"id":"2304.10351","title":"Inducing Stackelberg Equilibrium through Spatio-Temporal Sequential Decision-Making in Multi-Agent Reinforcement Learning","created":"2023-04-20","cited_by_count":5,"area":null},{"id":"2307.13158","title":"Multi-UAV Speed Control with Collision Avoidance and Handover-aware Cell Association: DRL with Action Branching","created":"2023-07-24","cited_by_count":5,"area":null},{"id":"2105.04077","title":"Dynamic Multichannel Access via Multi-agent Reinforcement Learning: Throughput and Fairness Guarantees","created":"2021-05-10","cited_by_count":4,"area":null},{"id":"2301.11510","title":"Exploring Deep Reinforcement Learning for Holistic Smart Building Control","created":"2023-01-27","cited_by_count":4,"area":null},{"id":"2305.19891","title":"Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2109.08512","title":"Soft Actor-Critic With Integer Actions","created":"2021-09-17","cited_by_count":3,"area":null},{"id":"2311.16895","title":"Optimization Theory Based Deep Reinforcement Learning for Resource Allocation in Ultra-Reliable Wireless Networked Control Systems","created":"2023-11-28","cited_by_count":3,"area":null},{"id":"2201.07916","title":"PROMPT: Learning Dynamic Resource Allocation Policies for Network Applications","created":"2022-01-19","cited_by_count":2,"area":null},{"id":"2209.09329","title":"MAN: Multi-Action Networks Learning","created":"2022-09-19","cited_by_count":2,"area":null},{"id":"2304.08769","title":"Cooperative Multi-Agent Reinforcement Learning for Inventory Management","created":"2023-04-18","cited_by_count":2,"area":null},{"id":"2310.17491","title":"FedPEAT: Convergence of Federated Learning, Parameter-Efficient Fine Tuning, and Emulator Assisted Tuning for Artificial Intelligence Foundation Models with Mobile Edge Computing","created":"2023-10-26","cited_by_count":2,"area":null},{"id":"2408.04251","title":"Cooperative Multi-Agent Deep Reinforcement Learning in Content Ranking Optimization","created":"2024-08-08","cited_by_count":2,"area":null},{"id":"2108.05701","title":"An Approach to Partial Observability in Games: Learning to Both Act and Observe","created":"2021-08-11","cited_by_count":1,"area":null},{"id":"2308.10203","title":"Soft Decomposed Policy-Critic: Bridging the Gap for Effective Continuous Control with Discrete RL","created":"2023-08-20","cited_by_count":1,"area":null},{"id":"2309.13955","title":"Deep Reinforcement Learning for the Heat Transfer Control of Pulsating Impinging Jets","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2602.02959","title":"Human-Centric Traffic Signal Control for Equity: A Multi-Agent Action Branching Deep Reinforcement Learning Approach","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2607.09078","title":"Toward Active Object Detection for UAVs in the Wild: A Large-Scale Dataset, Benchmark and Method","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2110.10632","title":"More Efficient Exploration with Symbolic Priors on Action Sequence Equivalences","created":"2021-10-20","cited_by_count":0,"area":null},{"id":"2207.14017","title":"Unsupervised Frequent Pattern Mining for CEP","created":"2022-07-28","cited_by_count":0,"area":null},{"id":"2209.01876","title":"SlateFree: a Model-Free Decomposition for Reinforcement Learning with Slate Actions","created":"2022-09-05","cited_by_count":0,"area":null},{"id":"2304.04797","title":"RAPID: Enabling Fast Online Policy Learning in Dynamic Public Cloud Environments","created":"2023-04-10","cited_by_count":0,"area":null},{"id":"2306.10787","title":"Adaptive Ordered Information Extraction with Deep Reinforcement Learning","created":"2023-06-19","cited_by_count":0,"area":null},{"id":"2308.14523","title":"Deep Reinforcement Learning for Uplink Scheduling in NOMA-URLLC Networks","created":"2023-08-28","cited_by_count":0,"area":null},{"id":"2312.16142","title":"A Bayesian Framework of Deep Reinforcement Learning for Joint O-RAN/MEC Orchestration","created":"2023-12-26","cited_by_count":0,"area":null},{"id":"2405.18733","title":"Efficient Learning in Chinese Checkers: Comparing Parameter Sharing in Multi-Agent Reinforcement Learning","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2409.18735","title":"Autoregressive Policy Optimization for Constrained Allocation Tasks","created":"2024-09-27","cited_by_count":0,"area":null},{"id":"2502.00288","title":"Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network","created":"2025-02-01","cited_by_count":0,"area":null},{"id":"2505.12759","title":"Your Offline Policy is Not Trustworthy: Bilevel Reinforcement Learning for Sequential Portfolio Optimization","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2507.22782","title":"Enhancing Multi-Agent Collaboration with Attention-Based Actor-Critic Policies","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2509.21211","title":"Evading Overlapping Community Detection via Proxy Node Injection","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2510.01508","title":"Realistic CDSS Drug Dosing with End-to-end Recurrent Q-learning for Dual Vasopressor Control","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2604.27162","title":"A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.11509","title":"Hierarchical LLM-Driven Control for HAPS-Assisted UAV Networks: Joint Optimization of Flight and Connectivity","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.10979","title":"Bellman-Taylor Score Decoding for Markov Decision Processes with State-Dependent Feasible Action Sets","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2608.25246","title":"ShuttleArena: Interpretable Self-Play in Physics-Based Badminton","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}